bioregistry 0.13.9__tar.gz → 0.13.10__tar.gz

{bioregistry-0.13.9 → bioregistry-0.13.10}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: bioregistry
-Version: 0.13.9
+Version: 0.13.10
 Summary: Integrated registry of biological databases and nomenclatures
 Keywords: snekpack,cookiecutter,databases,biological databases,biomedical databases,persistent identifiers
 Author: Charles Tapley Hoyt

{bioregistry-0.13.9 → bioregistry-0.13.10}/pyproject.toml

@@ -10,7 +10,7 @@ markers = [
 
 [project]
 name = "bioregistry"
-version = "0.13.9"
+version = "0.13.10"
 description = "Integrated registry of biological databases and nomenclatures"
 readme = "README.md"
 authors = [
@@ -254,7 +254,7 @@ known-first-party = [
 docstring-code-format = true
 
 [tool.bumpversion]
-current_version = "0.13.9"
+current_version = "0.13.10"
 parse = "(?P<major>\\d+)\\.(?P<minor>\\d+)\\.(?P<patch>\\d+)(?:-(?P<release>[0-9A-Za-z-]+(?:\\.[0-9A-Za-z-]+)*))?(?:\\+(?P<build>[0-9A-Za-z-]+(?:\\.[0-9A-Za-z-]+)*))?"
 serialize = [
     "{major}.{minor}.{patch}-{release}+{build}",

{bioregistry-0.13.9 → bioregistry-0.13.10}/src/bioregistry/__init__.py

@@ -127,7 +127,7 @@ from .resolve_identifier import (
     standardize_identifier,
 )
 from .resource_manager import Manager, manager
-from .schema.struct import (
+from .schema import (
     Author,
     Collection,
     Context,

{bioregistry-0.13.9 → bioregistry-0.13.10}/src/bioregistry/analysis/paper_ranking.py

@@ -400,7 +400,7 @@ def predict_and_save(
     :param path: Path to save the predictions.
     """
     x_meta = pd.DataFrame()
-    x_transformed = vectorizer.transform(df["title"] + " " + df["abstract"])
+    x_transformed = vectorizer.transform(_concat(df))
     for name, clf in classifiers:
         x_meta[name] = _predict(clf, x_transformed)
 
@@ -524,7 +524,7 @@ def train(
     df = pd.concat(curated_dfs)[["pubmed", "title", "abstract", "relevant"]]
 
     df["abstract"] = df["abstract"].fillna("")
-    df["title_abstract"] = df["title"] + " " + df["abstract"]
+    df["title_abstract"] = _concat(df)
     df = df[df.title_abstract.notna()]
     df = df.drop_duplicates()
     _echo_stats(df, "combine curated publications")
@@ -582,5 +582,9 @@ def train(
     return TrainingResult(curated_pubmed_ids, vectorizer, classifiers, meta_clf)
 
 
+def _concat(df: pd.DataFrame) -> pd.Series[str]:
+    return cast("pd.Series[str]", df["title"]) + " " + cast("pd.Series[str]", df["abstract"])
+
+
 if __name__ == "__main__":
     main()

{bioregistry-0.13.9 → bioregistry-0.13.10}/src/bioregistry/app/api.py

@@ -19,8 +19,7 @@ from ..export.rdf_export import (
     resource_to_rdf_str,
 )
 from ..resource_manager import Manager
-from ..schema import Attributable, sanitize_mapping
-from ..schema.struct import Collection, Context, Registry, Resource
+from ..schema import Attributable, Collection, Context, Registry, Resource, sanitize_mapping
 from ..schema_utils import (
     read_collections_contributions,
     read_prefix_contacts,

{bioregistry-0.13.9 → bioregistry-0.13.10}/src/bioregistry/app/ui.py

@@ -38,9 +38,8 @@ from ..export.rdf_export import (
     metaresource_to_rdf_str,
     resource_to_rdf_str,
 )
-from ..schema import Context
-from ..schema.constants import SCHEMA_TERMS
-from ..schema.struct import (
+from ..schema import (
+    Context,
     Registry,
     RegistryGovernance,
     RegistryQualities,
@@ -49,6 +48,7 @@ from ..schema.struct import (
     get_json_schema,
     schema_status_map,
 )
+from ..schema.constants import SCHEMA_TERMS
 from ..schema_utils import (
     read_collections_contributions,
     read_context_contributions,

{bioregistry-0.13.9 → bioregistry-0.13.10}/src/bioregistry/bibliometrics.py

@@ -8,7 +8,7 @@ from collections.abc import Iterable
 from typing import TYPE_CHECKING
 
 from .resource_manager import manager
-from .schema.struct import Publication, deduplicate_publications
+from .schema import Publication, deduplicate_publications
 
 if TYPE_CHECKING:
     import pandas

{bioregistry-0.13.9 → bioregistry-0.13.10}/src/bioregistry/cli.py

@@ -8,7 +8,7 @@ from .app.cli import web
 from .compare import compare
 from .export.cli import export
 from .lint import lint
-from .schema.struct import generate_schema
+from .schema import generate_schema
 from .utils import get_hexdigests, secho
 from .validate.cli import validate
 from .version import VERSION

{bioregistry-0.13.9 → bioregistry-0.13.10}/src/bioregistry/curation/add_cessda.py

@@ -13,7 +13,7 @@ from tabulate import tabulate
 from tqdm import tqdm
 
 import bioregistry
-from bioregistry.schema.struct import Author, Organization
+from bioregistry.schema import Author, Organization
 
 BASE = "https://vocabularies.cessda.eu"
 MODULE = pystow.module("cessda")

{bioregistry-0.13.9 → bioregistry-0.13.10}/src/bioregistry/curation/add_provider_status_curations.py

@@ -8,7 +8,7 @@ import pandas as pd
 from tqdm import tqdm
 
 from bioregistry import manager
-from bioregistry.schema.struct import StatusCheck
+from bioregistry.schema import StatusCheck
 
 URL = "https://docs.google.com/spreadsheets/d/e/2PACX-1vSC8RAMlNGauLHJb1RGwFuvC2LBJBjeeICRtq596npE6G4ZjZwX8W_Fz031hAfqsbu6f9Ruxl2PTsFx/pub?gid=1207894592&single=true&output=tsv"
 

{bioregistry-0.13.9 → bioregistry-0.13.10}/src/bioregistry/curation/clean_publications.py

@@ -7,7 +7,7 @@
 import click
 
 import bioregistry
-from bioregistry.schema.struct import deduplicate_publications
+from bioregistry.schema import deduplicate_publications
 
 
 @click.command()

{bioregistry-0.13.9 → bioregistry-0.13.10}/src/bioregistry/curation/enrich_publications.py

@@ -13,7 +13,7 @@ from manubot.cite.pubmed import get_pmid_for_doi, get_pubmed_csl_item
 from tqdm import tqdm
 
 from bioregistry import manager
-from bioregistry.schema.struct import Publication, deduplicate_publications
+from bioregistry.schema import Publication, deduplicate_publications
 from bioregistry.utils import removeprefix
 
 

{bioregistry-0.13.9 → bioregistry-0.13.10}/src/bioregistry/data/bioregistry.json

@@ -10915,15 +10915,38 @@
       "orcid": "0000-0003-4423-4370"
     },
     "description": "Bioschemas aims to improve the Findability on the Web of life sciences resources such as datasets, software, and training materials. It does this by encouraging people in the life sciences to use Schema.org markup in their websites so that they are indexable by search engines and other services. Bioschemas encourages the consistent use of markup to ease the consumption of the contained markup across many sites. This structured information then makes it easier to discover, collate, and analyse distributed resources. [from BioSchemas.org]",
+    "download_rdf": "https://bioschemas.org/types/bioschemas_types.ttl",
     "example": "Dataset",
     "homepage": "https://bioschemas.org",
     "mappings": {
       "biolink": "bioschemas"
     },
     "name": "BioSchemas",
+    "providers": [
+      {
+        "code": "draft",
+        "description": "BioSchemas makes a difference between its draft and released terms by putting them in different namespaces. This causes problems when consuming it, so this URI format maps them all into a unified semantic space",
+        "homepage": "https://bioschemas.org",
+        "name": "BioSchemas Draft",
+        "uri_format": "https://bioschemas.org/draft_terms/$1"
+      },
+      {
+        "code": "w3id",
+        "uri_format": "https://w3id.org/bioschemas/terms/$1"
+      },
+      {
+        "code": "term",
+        "uri_format": "https://bioschemas.org/terms/$1"
+      },
+      {
+        "code": "biothings",
+        "uri_format": "https://discovery.biothings.io/view/bioschemastypes/$1"
+      }
+    ],
     "repository": "https://github.com/BioSchemas/specifications",
     "synonyms": [
-      "bioschema"
+      "bioschema",
+      "bioschemas_draft"
     ],
     "twitter": "bioschemas",
     "uri_format": "https://bioschemas.org/profiles/$1"
@@ -18388,6 +18411,8 @@
       "name": "Charles Tapley Hoyt",
       "orcid": "0000-0003-4423-4370"
     },
+    "description": "A data model for managing information about chemical entities, ranging from atoms through molecules to complex mixtures.",
+    "download_owl": "https://raw.githubusercontent.com/chemkg/chemrof/main/schema/owl/chemrof.owl.ttl",
     "example": "FullySpecifiedAtom",
     "homepage": "https://chemkg.github.io/chemrof/",
     "mappings": {
@@ -39764,6 +39789,31 @@
     "homepage": "https://www.ema.europa.eu/en/medicines",
     "name": "European Medicines Evaluation Agency"
   },
+  "emg": {
+    "contact": {
+      "email": "oonagh.mannix@helmholtz-berlin.de",
+      "name": "Oonagh Brendike-Mannix",
+      "orcid": "0000-0003-0575-2853"
+    },
+    "contributor": {
+      "email": "cthoyt@gmail.com",
+      "github": "cthoyt",
+      "name": "Charles Tapley Hoyt",
+      "orcid": "0000-0003-4423-4370"
+    },
+    "description": "The Electron Microscopy (EM) Glossary is a widespread community effort to harmonize terminology in the electron and ion microscopies. It is created in a not-for profit collaboration between academic and non-university research institutions including domain and metadata experts. It provides harmonized terminology for application level semantic artifacts to source from and align with. [from homepage]",
+    "download_owl": "https://owl.emglossary.helmholtz-metadaten.de/ontology.owl",
+    "download_rdf": "https://owl.emglossary.helmholtz-metadaten.de/ontology.ttl",
+    "example": "00000005",
+    "homepage": "https://purls.helmholtz-metadaten.de/emg",
+    "license": "CC-BY-4.0",
+    "logo": "https://codebase.helmholtz.cloud/em_glossary/em_glossary/-/raw/main/EMGlossary.png",
+    "name": "Electron Microscopy Glossary",
+    "pattern": "^\\d{8}$",
+    "rdf_uri_format": "https://purls.helmholtz-metadaten.de/emg/EMG_$1",
+    "repository": "https://codebase.helmholtz.cloud/em_glossary/em_glossary",
+    "uri_format": "https://purls.helmholtz-metadaten.de/emg/EMG_$1"
+  },
   "emi": {
     "contact": {
       "email": "Tarcisio.Mendes@sib.swiss",

{bioregistry-0.13.9 → bioregistry-0.13.10}/src/bioregistry/data/collections.json

@@ -1196,6 +1196,22 @@
         "nfdi4culture.cto",
         "premis"
       ]
+    },
+    {
+      "authors": [
+        {
+          "email": "cthoyt@gmail.com",
+          "github": "cthoyt",
+          "name": "Charles Tapley Hoyt",
+          "orcid": "0000-0003-4423-4370"
+        }
+      ],
+      "description": "Prefixes for ontologies relevant for DAPHNE4NFDI.",
+      "identifier": "0000026",
+      "name": "DAPHNE4NFDI Ontologies",
+      "resources": [
+        "emg"
+      ]
     }
   ]
 }

{bioregistry-0.13.9 → bioregistry-0.13.10}/src/bioregistry/export/rdf_export.py

@@ -32,6 +32,7 @@ from ..constants import (
     SCHEMA_TURTLE_PATH,
 )
 from ..resource_manager import Manager, manager
+from ..schema import Collection, Registry, Resource
 from ..schema.constants import (
     ROR,
     WIKIDATA,
@@ -42,7 +43,6 @@ from ..schema.constants import (
     bioregistry_schema,
     get_schema_rdf,
 )
-from ..schema.struct import Collection, Registry, Resource
 
 logger = logging.getLogger(__name__)
 

{bioregistry-0.13.9 → bioregistry-0.13.10}/src/bioregistry/export/tables_export.py

@@ -14,7 +14,7 @@ from ..constants import (
     TABLES_SUMMARY_LATEX_PATH,
 )
 from ..resolve import count_mappings
-from ..schema.struct import Registry
+from ..schema import Registry
 from ..schema_utils import read_metaregistry
 from ..summary import BioregistrySummary
 

{bioregistry-0.13.9 → bioregistry-0.13.10}/src/bioregistry/record_accumulator.py

@@ -12,7 +12,7 @@ import curies
 from curies import Converter, Record
 from curies.w3c import NCNAME_RE
 
-from .schema.struct import Resource
+from .schema import Resource
 
 __all__ = [
     "get_converter",

{bioregistry-0.13.9 → bioregistry-0.13.10}/src/bioregistry/resolve.py

@@ -11,8 +11,7 @@ from typing import Any, Literal, overload
 import curies
 
 from .resource_manager import MetaresourceAnnotatedValue, manager
-from .schema import Attributable, Resource
-from .schema.struct import AnnotatedURL, Collection
+from .schema import AnnotatedURL, Attributable, Collection, Resource
 
 __all__ = [
     "add_resource",

{bioregistry-0.13.9 → bioregistry-0.13.10}/src/bioregistry/resource_manager.py

@@ -44,11 +44,11 @@ from .schema import (
     Attributable,
     Collection,
     Context,
+    MetaprefixAnnotatedValue,
     Registry,
     Resource,
     sanitize_model,
 )
-from .schema.struct import MetaprefixAnnotatedValue
 from .schema_utils import (
     _collections_from_path,
     _contexts_from_path,

bioregistry-0.13.10/src/bioregistry/schema/__init__.py

@@ -0,0 +1,50 @@
+"""Data structures."""
+
+from .struct import (
+    AnnotatedURL,
+    Attributable,
+    Author,
+    Collection,
+    Context,
+    MetaprefixAnnotatedValue,
+    Organization,
+    Provider,
+    Publication,
+    RDFFormat,
+    Registry,
+    RegistryGovernance,
+    RegistryQualities,
+    RegistrySchema,
+    Resource,
+    StatusCheck,
+    deduplicate_publications,
+    generate_schema,
+    get_json_schema,
+    schema_status_map,
+)
+from .utils import sanitize_mapping, sanitize_model
+
+__all__ = [
+    "AnnotatedURL",
+    "Attributable",
+    "Author",
+    "Collection",
+    "Context",
+    "MetaprefixAnnotatedValue",
+    "Organization",
+    "Provider",
+    "Publication",
+    "RDFFormat",
+    "Registry",
+    "RegistryGovernance",
+    "RegistryQualities",
+    "RegistrySchema",
+    "Resource",
+    "StatusCheck",
+    "deduplicate_publications",
+    "generate_schema",
+    "get_json_schema",
+    "sanitize_mapping",
+    "sanitize_model",
+    "schema_status_map",
+]

{bioregistry-0.13.9 → bioregistry-0.13.10}/src/bioregistry/schema/struct.py

@@ -56,9 +56,12 @@ __all__ = [
     "Organization",
     "Provider",
     "Publication",
+    "RDFFormat",
     "Registry",
     "Resource",
     "ResourceStatus",
+    "StatusCheck",
+    "deduplicate_publications",
     "get_json_schema",
 ]
 

{bioregistry-0.13.9 → bioregistry-0.13.10}/src/bioregistry/version.py

@@ -11,7 +11,7 @@ __all__ = [
     "get_version",
 ]
 
-VERSION = "0.13.9"
+VERSION = "0.13.10"
 
 
 def get_git_hash() -> str | None:

bioregistry-0.13.9/src/bioregistry/schema/__init__.py

@@ -1,26 +0,0 @@
-"""Data structures."""
-
-from .struct import (
-    Attributable,
-    Author,
-    Collection,
-    Context,
-    Publication,
-    Registry,
-    Resource,
-    get_json_schema,
-)
-from .utils import sanitize_mapping, sanitize_model
-
-__all__ = [
-    "Attributable",
-    "Author",
-    "Collection",
-    "Context",
-    "Publication",
-    "Registry",
-    "Resource",
-    "get_json_schema",
-    "sanitize_mapping",
-    "sanitize_model",
-]